Server facts
prode-mcp
Project
- Author
- CuriousBox-AI
- Repository
- github.com/CuriousBox-AI/ProdE-mcp
- License
- Not specified
- Category
- Developer Tools
Tech
- Runtime / language
- Not specified
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 6
- Last commit
- Data as of
Tags
- ai coding assistant
- mcp
- prode
Overview
Cross-service development often requires following behavior beyond a single repository. ProdE exposes a knowledge layer of selected codebases to coding assistants, supporting investigations into authentication flows, internal APIs, shared dependencies, and distributed failures. Developers can list available repositories, locate relevant documentation and code symbols with get_high_level_context, then retrieve full documents through get_documentations. Documentation trees provide another way to navigate repository knowledge. This workflow connects broad discovery with the source material needed to examine implementation details, whether the question concerns an individual project or behavior spanning several services.
For source-level investigation, the toolset includes regex content searches, glob-based file discovery, file reading, directory inspection, and symbol-reference lookup. Content searches and file discovery can span selected repositories or all team repositories. A sandbox shell supports repository exploration and session notes, with read-only repository access and no network access. Setup involves a ProdE account, connecting GitHub or Bitbucket, selecting repositories for indexing, and obtaining a dashboard authentication token. Listed assistant integrations include Cursor, Cline, GitHub Copilot in VS Code, and Windsurf.
prode-mcp setup notes
- prode-mcp records stdio only; confirm a network transport upstream before planning remote access.
- prode-mcp has no recorded license; confirm reuse terms in its repository.